Dynamic Driving Scenes

Follow this topic Ask about this topic

Momentum

2 papers in the last four weeks, against 2 the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 26

All topics

Controllable and Photorealistic Pedestrian Risky Motion Generation for End-to-End Driving Safety Evaluation
Oct 5, 2026Siyuan Liu, Miao Li, Haibao Yu +4Dynamic Driving Scenes
School of Vehicle and Mobility, Tsinghua University · Carnegie Mellon University · State Key Laboratory of Intelligent Green Vehicle and Mobility, Tsinghua University
DyRAD: Radar Novel View Synthesis for Dynamic Driving Scenes
Sep 30, 2026Merav Keidar, Tomer Borreda, Rajalakshmi Nandakumar +1Radar Dynamic Driving Scenes
Technion · Cornell Tech · NVIDIA
Quantifying Spectral Differences in Vehicle Kinematics Between Production Autonomous and Human-Driven Vehicles Across Driving Scenarios
Sep 11, 2026Peiyi Fang, Xiangyu Li, Yonglin Weng +1Dynamic Driving Scenes Traffic
The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, 511453, China
Long-Horizon Consistent and Interaction-Aware World Models for Multi-Style End-to-End Driving
Sep 3, 2026Yuxuan Han, Kunyuan Wu, Liyunong Yang +4Autonomous Driving Dynamic Driving Scenes
School of Intelligence Science and Engineering, Harbin Institute of Technology, Shenzhen, China · Autonomous Driving Center, Shanghai Utopilot Technology Co.Ltd., China
CRUISE: Vision-Language Model-Guided Uncertainty-Aware Cross-Modal Sensor Fusion for Robust Autonomous Driving
Aug 10, 2026Junyao Wang, Yulin Xu, Yu Li +2Multi-Sensor Fusion Uncertainty-Aware Fusion
Department of Computer Science, University of California, Irvine, 92697, USA · Department of Electrical Engineering and Computer Science, University of California, Irvine, 92697, USA · Department of Computer Science, the Department of Electrical Engineering and Computer Science, and the Department of Mechanical and Aerospace Engineering, University of California, Irvine, 92697, USA
muSync-GS: Physics-Synchronized Driving Video Synthesis for Weather and Geometric Road Hazards
Aug 5, 2026Yang Chen, Yicheng Zhu, Tao Li +1Dynamic Driving Scenes Vehicle Dynamics
Rochester Institute of Technology · City University of Hong Kong
RealWeather: Realistic and Scene-Faithful Weather Translation with Driving World Models
Aug 3, 2026Yuwei Ning, Liangzhi Wang, Yi Xiao +5Dynamic Driving Scenes Synthetic-To-Real Domain Gap
1Sun Yat-sen University · 2Shenzhen Loop Area Institute
Emergent Autonomous Drifting for Collision Avoidance in Real-World Winter Driving Scenarios
Jul 21, 2026Elliot Weiss, Michael Thompson, Thomas Lew +1Vehicle Dynamics Collision Avoidance
Toyota Research Institute.
Benchmarking the Robustness of Autonomous Driving to Environmental Illusions: A Lane Perception Perspective
Jul 7, 2026Tianyuan Zhang, Xianglong Liu, Aishan Liu +6Autonomous Driving Perception Dynamic Driving Scenes
SKLCCSE, the School of Computer Science and Engineering, Beihang University, Beijing 100191, China · School of Cyber Science and Technology, Sun Yat-sen University, Shenzhen 518107, China · Henan University of Science and Technology, Luoyang 471023, China +2
Search-based Testing of Vision Language Models for In-Car Scene Understanding
Jul 2, 2026Lev Sorokin, Chen Yang, Ken E. Friedl +1Dynamic Driving Scenes Recent Vision-Language Models
BMW Group, Technical University of Munich · Munich, Germany · Technical University of Munich +2
CommonRoad-Game: A Human-in-the-Loop Simulation Framework for Autonomous Driving
Jul 1, 2026Yunfei Bi, Youran WangAutonomous Driving Simulation Autonomous Driving
Technical University of Munich Munich, Germany
Reliability-Aware Monocular Depth Supervision for Sparse-View Neural Reconstruction
Jun 27, 2026Wei-Teng Chu, Yashasvini Gopalan, Changju YuanMonocular Depth Estimation Sparse-View
Stanford University
DrivingVoxels: Compositional Sparse Voxel Rasterization for Dynamic Driving Scene Reconstruction
Jun 22, 2026Tania Aguirre, Luis Roldão, Moussab Bennehar +4Dynamic Driving Scenes Voxel
Noah’s Ark, Huawei Paris Research Center, France · EURECOM, France
RealityBridge: Bridging Editable 3D Gaussian Splatting Driving Simulations and Real-World Videos
Jun 15, 2026Zhenhua Wu, Yun Pang, Mingkun Chang +4Dynamic Driving Scenes Scene Reconstruction
1Sun Yat-sen University · 2Shanghai Innovation Institute · 3Shenzhen Loop Area Institute
Lane Change Trajectory Planning for Personalized Driving Comfort and Mobility Efficiency
Jun 5, 2026Haoxuan Dong, Dongjun Li, Ziyou SongMobility Single Trajectory
Department of Mechanical Engineering National University of Singapore Singapore 117575, Singapore · Department of Electrical Engineering and Computer Science University of Michigan Ann Arbor, MI 48109, USA
V2XCrafter: Learning to Generate Driving Scene Across Agents
May 28, 2026Yihang Tao, Yu Guo, Senkang Hu +4Dynamic Driving Scenes Indoor Scene Generation
Hong Kong JC STEM Lab of Smart City · City University of Hong Kong · Lingnan University
Physics-Aware 3D Gaussian Editing for Driving Scene Generation
May 25, 2026Feng Zhou, Jian Zhang, Yuhang Sun +5Dynamic Driving Scenes Road Networks
School of Artificial Intelligence, Jilin University, Changchun, China. · China FAW Group Co., Ltd., Changchun, China. · National Key Laboratory of Automotive Chassis Integration and Bionics, Jilin University, Changchun, China.
Grounding Driving VLA via Inverse Kinematics
May 20, 2026Junsung Park, Hyunjung ShimDynamic Driving Scenes Trajectory Generation
Korea Advanced Institute of Science and Technology KimJaeChul AI Graduate School 18, Taebong-ro, Seocho-gu, Seoul, South Korea
Real2Sim: A Physics-driven and Editable Gaussian Splatting Framework for Autonomous Driving Scenes
May 13, 2026Kaicong Huang, Talha Azfar, Weisong Shi +1Dynamic Driving Scenes Waymo Open Motion Dataset
Department of Civil and Environmental Engineering, Rensselaer Polytechnic Institute, 110 Eighth Street, Troy, NY USA 12180. · Department of Computer and Information Sciences, University of Delaware, Newark, DE USA 19716.
ConFixGS: Learning to Fix Feedforward 3D Gaussian Splatting with Confidence-Aware Diffusion Priors in Driving Scenes
May 10, 2026Rui Song, Tianhui Cai, Markus Gross +5Feed-Forward 3D Gaussian Splatting Feed-Forward 3D Gaussian
University of California, Los Angeles · Technical University of Munich · University of Cambridge
Unified Modeling of Lane and Lane Topology for Driving Scene Reasoning
May 9, 2026Han Li, Yulu Gao, Si Liu +3Communication Topologies Dynamic Driving Scenes
School of Artificial Intelligence, Beihang University, Beijing, China · Zhongguancun Academy, Beijing, China · Hangzhou International Innovation Institute, Beihang University, Hangzhou, China +1
One World, Dual Timeline: Decoupled Spatio-Temporal Gaussian Scene Graph for 4D Cooperative Driving Reconstruction
May 8, 2026Yulong Chen, Xiaoyun Dong, Haoyu Zhang +6Dynamic Driving Scenes Spatio-Temporal Scene Graphs
City University of Hong Kong (Dongguan), Guangdong, China · City University of Hong Kong, Hong Kong, China · SLAI, Shenzhen, China
The Field of Safe Motion: Operationalizing Affordances in the Field of Safe Travel Using Reachability Analysis
Apr 29, 2026Leif Johnson, Trent Victor, Johan EngströmReachability Human Driving
Waymo LLC, 1600 Amphitheatre Parkway, Mountain View, California 94043 USA
Learning from the Unseen: Generative Data Augmentation for Geometric-Semantic Accident Anticipation
Apr 29, 2026Yanchen Guan, Haicheng Liao, Chengyue Wang +4Accident Source Term Evaluation Code Autonomous Driving
State Key Laboratory of Internet of Things for Smart City, University of Macau, Macau SAR, 999078, China. · Department of Civil Engineering, University of Macau, Macau SAR, 999078, China. · Department of Computer and Information Science, University of Macau, Macau SAR, 999078, China. +1
Unposed-to-3D: Learning Simulation-Ready Vehicles from Real-World Images
Apr 21, 2026Hongyuan Liu, Bochao Zou, Qiankun Liu +10Dynamic Driving Scenes 3D Reconstruction
University of Science and Technology Beijing · Li Auto Inc.
Seed-to-Seed: Unpaired Image Translation in Diffusion Seed Space
Sep 1, 2024Or Greenberg, Eran Kishon, Dani LischinskiUnpaired Image-To-Image Translation Diffusion Models
General Motors R&D · The Hebrew University of Jerusalem

Oct 5, 2026, cs.ROJ/K move · Enter open · S save

Controllable and Photorealistic Pedestrian Risky Motion Generation for End-to-End Driving Safety Evaluation

Siyuan Liu, Miao Li, Haibao Yu, Haohong Lin+3

School of Vehicle and Mobility, Tsinghua University · Carnegie Mellon University · State Key Laboratory of Intelligent Green Vehicle and Mobility, Tsinghua University

Dynamic Driving Scenes

Open paper AskPDF arXiv

Evaluating end-to-end autonomous driving under rare, safety-critical vehicle-pedestrian interactions requires photorealistic, sensor-level scenarios. However, trajectory-based scenario generators cannot synthesize raw visual observations, whereas video-based approaches lack controllability. To bridge this gap, we present ControlPed, a novel framework that combines trajectory-level conflict synthesis with 3D Gaussian Splatting (3DGS) to generate photorealistic, motion-controllable safety-critical scenarios. Built upon HazardPed, a dataset derived from 10,352 traffic videos comprising 422 conflict trajectories, HD maps, and 857 annotated 3D human motions, ControlPed first generates conflict trajectories, lifts them into 3D human motion sequences via text-conditioned motion diffusion, and finally renders multi-view sensor observations using animatable 3DGS avatars. Safety evaluation in 88 rendered photorealistic scenarios reveals that seven leading end-to-end driving models suffer a severe performance drop, with their mean HDScore plunging from 88.8 to 47.4, exposing major failure modes under dangerous pedestrian behaviors. The dataset and testing benchmarks will be released to facilitate safety assessment of vehicle-pedestrian interactions.

Momentum

Related topics

Latest papers 26